chiark / gitweb /
new unicode string iterator give cleaner boundary testing
[disorder] / lib / unicode.h
... / ...
CommitLineData
1/*
2 * This file is part of DisOrde
3 * Copyright (C) 2007 Richard Kettlewell
4 *
5 * This program is free software; you can redistribute it and/or modify
6 * it under the terms of the GNU General Public License as published by
7 * the Free Software Foundation; either version 2 of the License, or
8 * (at your option) any later version.
9 *
10 * This program is distributed in the hope that it will be useful, but
11 * WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 * General Public License for more details.
14 *
15 * You should have received a copy of the GNU General Public License
16 * along with this program; if not, write to the Free Software
17 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
18 * USA
19 */
20/** @file lib/unicode.h
21 * @brief Unicode support functions
22 */
23
24#ifndef UNICODE_H
25#define UNICODE_H
26
27/** @brief Smart pointer into a string
28 *
29 * Iterators can be efficiently moved either forwards or back to the start of
30 * the string. They cannot (currently) efficiently be moved backwards. Their
31 * advantage is that they remember internal state to speed up boundary
32 * detection.
33 *
34 * Iterators can point to any code point of the string, or to a hypothetical
35 * post-final code point of value 0, but not outside the string.
36 */
37typedef struct utf32_iterator_data *utf32_iterator;
38
39char *utf32_to_utf8(const uint32_t *s, size_t ns, size_t *nd);
40uint32_t *utf8_to_utf32(const char *s, size_t ns, size_t *nd);
41
42size_t utf32_len(const uint32_t *s);
43int utf32_cmp(const uint32_t *a, const uint32_t *b);
44
45uint32_t *utf32_decompose_canon(const uint32_t *s, size_t ns, size_t *ndp);
46char *utf8_decompose_canon(const char *s, size_t ns, size_t *ndp);
47
48uint32_t *utf32_decompose_compat(const uint32_t *s, size_t ns, size_t *ndp);
49char *utf8_decompose_compat(const char *s, size_t ns, size_t *ndp);
50
51uint32_t *utf32_casefold_canon(const uint32_t *s, size_t ns, size_t *ndp);
52char *utf8_casefold_canon(const char *s, size_t ns, size_t *ndp);
53
54uint32_t *utf32_casefold_compat(const uint32_t *s, size_t ns, size_t *ndp);
55char *utf8_casefold_compat(const char *s, size_t ns, size_t *ndp);
56
57int utf32_is_grapheme_boundary(const uint32_t *s, size_t ns, size_t n);
58int utf32_is_word_boundary(const uint32_t *s, size_t ns, size_t n);
59
60utf32_iterator utf32_iterator_new(const uint32_t *s, size_t ns);
61void utf32_iterator_destroy(utf32_iterator it);
62
63size_t utf32_iterator_where(utf32_iterator it);
64int utf32_iterator_set(utf32_iterator it, size_t n);
65int utf32_iterator_advance(utf32_iterator it, size_t n);
66uint32_t utf32_iterator_code(utf32_iterator it);
67int utf32_iterator_grapheme_boundary(utf32_iterator it);
68int utf32_iterator_word_boundary(utf32_iterator it);
69
70#endif /* UNICODE_H */
71
72/*
73Local Variables:
74c-basic-offset:2
75comment-column:40
76fill-column:79
77indent-tabs-mode:nil
78End:
79*/